[Simh] What is the best machine to run simh?

[Zane H. Healy]

At 11:56 AM -0500 1/25/08, Boucher, François wrote:
>I see that the test results are extraordinary, but the time
>It took to run it - from 22:44:32 to 23:03:00 = 00:18:28
>is excessively long.  On the 31.2 simulated vax test machine, the
>pt_vax.exe test takes about 4 minutes to complete.
>
>In your text, you say you VESTed it.  What does that mean?
>
>I dispose of DEC500au alphastations to migrate simh to it if this
>could give us some good results, but altrough the benchmark
>Numbers are super good, the execution time does not match up with it.
>Are you able to use VMS VAX on your setup?  If yes, how much time does
>It take to do a VMS boot?

I'm afraid you appear to have misunderstood what 
I did.  I converted the VAX executable to an 
Alpha executable using the VEST tool that DEC 
released for migrating from VAX to Alpha.  So I 
ran it native on OpenVMS 8.3/Alpha, I'm not doing 
any emulation.

Your comments on the run time are most 
interesting.  I would suspect that the extra time 
might be spent in the Dhrystones routine, as 
there is quite obviously a problem there.  I was 
also surprised by how low the MIPS scores were. 
For VUPs it is worth remembering that 1 VUP is a 
measurement of more than just raw CPU speed.  The 
2GB of PC100 RAM, and U2W SCSI disks probably 
help as well.

BTW, the VUP score looks surprisingly close to 
what I would expect based on another tool that 
someone released years ago.

$ @vup
Approximate System VUPs Rating :  1387.0

Zane


-- 
| Zane H. Healy                    | UNIX Systems Administrator |
| healyzh at aracnet.com (primary)    | OpenVMS Enthusiast         |
| MONK::HEALYZH (DECnet)           | Classic Computer Collector |
+----------------------------------+----------------------------+
|     Empire of the Petal Throne and Traveller Role Playing,    |
|          PDP-10 Emulation and Zane's Computer Museum.         |
|                http://www.aracnet.com/~healyzh/               |